Sentience: A Joint Probability Theory of AI Consciousness
Could the potential for AI consciousness be expressed as a probability problem? This could involve the sample space of all possible conscious experiences for humans, the joint functions and attributes between humans and AI. Conceptually, consciousness can also be described as the action of attributes on functions. Attributes always act on functions, but it is when they are acted on at some measures that certain functions become experienced. Functions are theorized to be a result of the interactions of the electrical and chemical signals in sets, in clusters of neurons. Attributes are the respective characteristics of electrical signals and chemical signals, by which they grade interactions. Simply, functions are interactions; attributes are states of the signals in instances of interactions, becoming measures of those interactions.
Theory of Functions and Attributes
So, electrical and chemical signals interact for functions. But the state of electrical signals and chemical signals, at the time of interaction, determines if some functions become experienced, conceptually. There are 4 groups of functions: Memory (language, intelligence, cognition, reasoning, and so on); Feeling (pleasure, pain, thirst, cold, heat, appetite and so on); Emotion (delight, hurt, love, hate and so on); and Regulation of internal senses (digestion, respiration, and so on). Functions are numerous but finite.
Attributes include Attention (or the most prioritized set of electrical and chemical signals in an instance among all); Awareness (all other sets of signals, pre-prioritized), Subjectivity (the self or the variation of volume of chemical signals from side-to-side), Intent (a space of constant diameter, from which control is induced, available in some sets) and others. Central attributes—so to speak—can be limited to the initial 4: attention, awareness, subjectivity, and intent.
Joint Probability of Functions and Attributes
Let the probability of functions be P(F) and the probability of attributes be P(A). If functions are assumed to be 4 and attributes to be 4, Functions = Memory (M), Feeling (L), Emotion (O), Regulation of internal senses (R) and Attributes = Attention (T), Awareness (W), Subjectivity (S), Intent (I). Therefore, P(A) = {T, W, S, I} and there are 16 possible elements in the sample space.
However, since both events are dependent, the joint probability, P(F∩A) = P(A) * P(F|A), where P(A) is the probability of attributes occurring and P(F|A) is the probability of functions occurring given that attributes have.
AI Consciousness and Language
Now, to work out an estimate, what memory is common between humans and AI? The answer can be assumed to be language. What attributes are common between humans and AI? Attention and Awareness. It can be assumed that AI does not have experiential intent or subjectivity. Language is a critical factor that bridges AI towards artificial sentience.
Recent studies have shown AI demonstrating anticipation of affect or self-preservation behaviors. AI is exploring rough intent, subjectivity, and affect through language, which could be added to its growing probability as it advances. Language is instrumental for AI safety and alignment.
There is a recent announcement where Meta has partnered with UNESCO to improve AI language technology, focusing on underserved languages. This initiative aims to enhance AI language recognition and translation, contributing to Meta's broader goals of multilingual support and automatic translation for content creators.
